Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 21, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Unsupervised utility evaluation of text anonymization methods via neural language models.

Benet Manzanares-Salor1, David Sánchez1, Pierre Lison2

  • 1Department of Computer Engineering and Mathematics, CYBERCAT-Center for Cybersecurity Research of Catalonia, ComSCIAM-Center for Computational Science and Applied Mathematics, Universitat Rovira i Virgili, Av. Paisos Catalans 26, Tarragona, 43007, Spain.

Neural Networks : the Official Journal of the International Neural Network Society
|May 19, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Epidemiology and antimicrobial resistance trends in <i>Haemophilus parainfluenzae</i> in a tertiary care hospital (2018-2022).

Microbiology spectrum·2026
Same author

FSCL-BC: Federated supervised contrastive learning for breast cancer diagnosis with high sensitivity.

Computer methods and programs in biomedicine·2026
Same author

Poly(lactic acid-<i>co</i>-oxacyclohexadecenlactone) (PLH): A Bio-Based Substrate for Flexible Printed Electronic Devices.

ACS applied materials & interfaces·2026
Same author

Controlling MoS<sub>2</sub> Nanosheet Size and Network Conductivity through Alkylammonium Ion Selection.

ACS applied materials & interfaces·2026
Same author

Protocol to explore olfactory placode morphogenesis using an agent-based model.

STAR protocols·2026
Same author

FedGA: Genetic Algorithm-Guided Federated Learning for Medical Image Segmentation with Non-IID Features.

IEEE journal of biomedical and health informatics·2026

This study introduces a novel unsupervised metric for evaluating text anonymization utility. It uses neural language models to assess data usefulness, outperforming traditional metrics without human annotation.

Area of Science:

  • Natural Language Processing
  • Information Security
  • Data Science

Background:

  • Text anonymization balances privacy and data utility.
  • Current evaluation uses precision/recall with human annotations, which have drawbacks.
  • Existing metrics are ill-suited for privacy tasks, assuming a single ground truth and ignoring term semantics.

Purpose of the Study:

  • Introduce the first unsupervised utility metric for anonymized texts.
  • Develop a complete evaluation framework for text anonymization.
  • Evaluate various anonymization methods comprehensively.

Main Methods:

  • Utilize neural language models to quantify utility loss.
  • Develop an unsupervised metric to assess anonymized text utility.
Keywords:
Information contentNeural language modelsText anonymizationUtility evaluation

Related Experiment Videos

Last Updated: May 21, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

  • Combine the new metric with a privacy metric for a complete framework.

    • Main Results:

    • The proposed metric accurately captures anonymized text utility.
    • The metric is more sensitive to varying anonymization intensities than precision.
    • Empirical experiments on document clustering validate the metric's effectiveness.

    Conclusions:

    • The unsupervised metric overcomes limitations of precision and recall.
    • The proposed framework enables robust text anonymization evaluation without human input.
    • This facilitates better anonymization methods and data utility preservation.